XISM: an eXploratory and Interactive Graph Tool to Visualize and Evaluate Semantic Map Models

TL;DR

XISM tackles the tension between scalability and interpretability in semantic map models by marrying data-driven graph generation with expert refinement in an interactive, web-based tool. It builds candidate SMMs from a fully connected co-occurrence graph using maximum spanning trees, then uses an edge-merging step to guarantee 100% connectivity, with real-time evaluation metrics to guide refinement. The system balances efficiency and linguistic interpretability through a human-in-the-loop workflow and validates its approach with offline typological datasets and online expert studies, achieving high coverage, strong accuracy, and positive usability feedback. This work provides a practical, reusable framework for collaborative, explainable semantic-map construction across diverse linguistic domains.

Abstract

Semantic map models visualize systematic relations among semantic functions through graph structures and are widely used in linguistic typology. However, existing construction methods either depend on labor-intensive expert reasoning or on fully automated systems lacking expert involvement, creating a tension between scalability and interpretability. We introduce \textbf{XISM}, an interactive system that combines data-driven inference with expert knowledge. XISM generates candidate maps via a top-down procedure and allows users to iteratively refine edges in a visual interface, with real-time metric feedback. Experiments in three semantic domains and expert interviews show that XISM improves linguistic decision transparency and controllability in semantic-map construction while maintaining computational efficiency. XISM provides a collaborative approach for scalable and interpretable semantic-map building. The system\footnote{https://app.xism2025.xin/} , source code\footnote{https://github.com/hank317/XISM} , and demonstration video\footnote{https://youtu.be/m5laLhGn6Ys} are publicly available.

Figures (4)

• Figure 1: Overview of XISM
• Figure 2: XISM user interface and system walkthrough
• Figure 3: Comparison of normalized Div_D, Acc, and original computation time over different values of $K$.
• Figure 4: Survey summary from four dimensions